arXiv subjects

Matthias J. P. van Osch

Publications and source records attributed to Matthias J. P. van Osch.

6 recordsLinked to original sources

arXiv2026

Data-Efficient Networks for Multi-Contrast MRI Reconstruction based on a Generalized Content/Style Prior

Multi-contrast MR scans contain redundant structural information that can be leveraged during reconstruction and potentially accelerate acquisition times. This idea has inspired end-to-end guided reconstruction models, leveraging one or more contrasts to guide the reconstruction of a different contrast. However, these models require large paired multi-contrast raw datasets for training, limiting their application in low-data regimes. In this work, we propose a modular framework, namely CoSMo-RecNet, for learning guided reconstruction models in the low-data regime. At its core is a reusable multi-contrast representation based on a content/style model, which can be learned from large-scale, publicly accessible, unpaired multi-contrast image datasets, without available k-space data. Using this frozen model as a multi-contrast prior and using a set of reference contrasts, the reconstruction problem reduces to a much simpler refinement problem that can be solved by a lightweight unrolled network and thus learned from small, task-specific reconstruction datasets. We demonstrate the efficacy of CoSMo-RecNet by evaluating it on the low-field 0.3 T M4Raw dataset, showing stable reconstruction quality on decreasing the raw training data budget. CoSMo-RecNet achieved higher reconstruction quality with 5 training subjects or lower compared to a parameter-count-matched MoDL trained on 100 subjects. On a data-limited and severely out-of-distribution ultra-low-field 47 mT Halbach scanner dataset, CoSMo-RecNet was superior to other viable strategies, including classical reconstruction, transfer learning, and zero-shot reconstruction.

eess.IV↗

arXiv2025

UPCMR: A Universal Prompt-guided Model for Random Sampling Cardiac MRI Reconstruction

Cardiac magnetic resonance imaging (CMR) is vital for diagnosing heart diseases, but long scan time remains a major drawback. To address this, accelerated imaging techniques have been introduced by undersampling k-space, which reduces the quality of the resulting images. Recent deep learning advancements aim to speed up scanning while preserving quality, but adapting to various sampling modes and undersampling factors remains challenging. Therefore, building a universal model is a promising direction. In this work, we introduce UPCMR, a universal unrolled model designed for CMR reconstruction. This model incorporates two kinds of learnable prompts, undersampling-specific prompt and spatial-specific prompt, and integrates them with a UNet structure in each block. Overall, by using the CMRxRecon2024 challenge dataset for training and validation, the UPCMR model highly enhances reconstructed image quality across all random sampling scenarios through an effective training strategy compared to some traditional methods, demonstrating strong adaptability potential for this task.

cs.CV↗

arXiv2021

ASL to PET Translation by a Semi-supervised Residual-based Attention-guided Convolutional Neural Network

Positron Emission Tomography (PET) is an imaging method that can assess physiological function rather than structural disturbances by measuring cerebral perfusion or glucose consumption. However, this imaging technique relies on injection of radioactive tracers and is expensive. On the contrary, Arterial Spin Labeling (ASL) MRI is a non-invasive, non-radioactive, and relatively cheap imaging technique for brain hemodynamic measurements, which allows quantification to some extent. In this paper we propose a convolutional neural network (CNN) based model for translating ASL to PET images, which could benefit patients as well as the healthcare system in terms of expenses and adverse side effects. However, acquiring a sufficient number of paired ASL-PET scans for training a CNN is prohibitive for many reasons. To tackle this problem, we present a new semi-supervised multitask CNN which is trained on both paired data, i.e. ASL and PET scans, and unpaired data, i.e. only ASL scans, which alleviates the problem of training a network on limited paired data. Moreover, we present a new residual-based-attention guided mechanism to improve the contextual features during the training process. Also, we show that incorporating T1-weighted scans as an input, due to its high resolution and availability of anatomical information, improves the results. We performed a two-stage evaluation based on quantitative image metrics by conducting a 7-fold cross validation followed by a double-blind observer study. The proposed network achieved structural similarity index measure (SSIM), mean squared error (MSE) and peak signal-to-noise ratio (PSNR) values of $0.85\pm0.08$, $0.01\pm0.01$, and $21.8\pm4.5$ respectively, for translating from 2D ASL and T1-weighted images to PET data. The proposed model is publicly available via https://github.com/yousefis/ASL2PET.

eess.IV↗

arXiv2020

An Adaptive Intelligence Algorithm for Undersampled Knee MRI Reconstruction

Adaptive intelligence aims at empowering machine learning techniques with the additional use of domain knowledge. In this work, we present the application of adaptive intelligence to accelerate MR acquisition. Starting from undersampled k-space data, an iterative learning-based reconstruction scheme inspired by compressed sensing theory is used to reconstruct the images. We adopt deep neural networks to refine and correct prior reconstruction assumptions given the training data. The network was trained and tested on a knee MRI dataset from the 2019 fastMRI challenge organized by Facebook AI Research and NYU Langone Health. All submissions to the challenge were initially ranked based on similarity with a known groundtruth, after which the top 4 submissions were evaluated radiologically. Our method was evaluated by the fastMRI organizers on an independent challenge dataset. It ranked #1, shared #1, and #3 on respectively the 8x accelerated multi-coil, the 4x multi-coil, and the 4x single-coil track. This demonstrates the superior performance and wide applicability of the method.

eess.IV↗

arXiv2019

Adaptive-CS-Net: FastMRI with Adaptive Intelligence

Adaptive intelligence aims at empowering machine learning techniques with the extensive use of domain knowledge. In this work, we present the application of adaptive intelligence to accelerate MR acquisition. Starting from undersampled k-space data, an iterative learning-based reconstruction scheme inspired by compressed sensing theory is used to reconstruct the images. We adopt deep neural networks to refine and correct prior reconstruction assumptions given the training data. Our results show that an adaptive intelligence approach performs better than traditional methods as well as deep learning methods that do not take prior knowledge into account.

eess.IV↗

arXiv2019

Perfusion and apparent oxygenation in the human placenta (PERFOX)

Purpose: To study placental function - both perfusion and an oxygenation surrogate (T2*)-simultaneously and quantitatively in-vivo. Methods: 15 pregnant women were scanned on a 3T MR scanner. For perfusion measurements, a velocity selective arterial spin labelling preparation module was placed before a multi-echo gradient echo EPI readout to integrate T2* and perfusion measurements in one joint perfusion-oxygenation (PERFOX) acquisition. Joint motion correction and quantification were performed to evaluate changes in T2* and perfusion over GA. Results: The optimised integrated PERFOX protocol and post-processing allowed successful visualization and quantification of perfusion and T2* in all subjects. Areas of high T2* and high perfusion appear to correspond to placental sub-units and show a systematic offset in location along the maternal-fetal axis. The areas of highest perfusion are consistently closer to the maternal basal plate and the areas of highest T2* closer to the fetal chorionic plate. Quantitative results show a strong negative correlation of gestational age with T2* and weak negative correlation with perfusion. Conclusion: A strength of the joint sequence is that it provides truly simultaneous and co-registered estimates of local T2* and perfusion, however, to achieve this, the time per slice is prolonged compared to a perfusion only scan which can potentially limit coverage. The achieved interlocking can be particularly useful when quantifying transient physiological effects such as uterine contractions. PERFOX opens a new avenue to elucidate the relationship between maternal supply and oxygen uptake, both of which are central to placental function and dysfunction.

physics.med-ph↗